Claim · model-written summary
Cross-validation accuracy rose from 0.40 to 0.41 using diversity-panel lines to predict breeding lines.
- Taxon
- wheat
Triticum aestivumt0 - Outcome
- accuracye0
- Direction
- increasee0
- Value
- 0.40 to 0.41e0
- Comparator
- diversity panels linese0
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“There was an increase in accuracy using cross-validations from 0.40 to 0.41 using diversity panels lines to breeding lines.”
t0“wheat (Triticum aestivum L.)”
Title
Lance F. Merrick; Arron H. Carter The Plant Genome 2021. doi:10.1002/tpg2.20158
Other claims from this paper (5)
- Observation Only a few significant differences occurred among GS models.
- Method / resource Support vector machines attained the highest cross-validation accuracy, 0.56, in one breeding-line trial.
- Method / resource Parametric models had consistent moderate accuracy.
- Method / resource Nonparametric models had a slight accuracy increase when years were combined.
- Recommendation The authors concluded that breeders can implement GS for a complex trait with nonparametric models and gain accuracy by combining training populations over years.